Sober

I use pytorch=1.0.0 annd modify the code in 'nnet/py_factory.py' which import the 'from torch.nn import DataParallel' instead of 'from models.py_utils.data_parallel import DataParallel'

You can just modify your code in 'centernet_od/nnet/py_factory.py" The class __init__ part: ``` #train on multi-gpu self.network = Network(self.model, self.loss).cuda() #import 'from torch.nn import DataParallel' instead of 'from models.py_utils.data_parallel import...

I found this problem caused by `scipy\sparse`. I successfully compile the exe file according to two steps: 1. downgrade the scipy package to 1.4.1 by `pip install scipy==1.4.1` 2. add...

upstah sync failed in macos device, I test the connect is ok, but sync is not working, how to fix it ?

> 那肯定不能访问，你从头到尾frps服务端就没开过5000端口，http协议需要用域名，买个域名设置后用 xxx.com:7100 或者 https的 7200访问 您好，其实我之前是买过域名试验过的，也是不可以，这是我根据您的描述重新配置的frpc.toml文件，修改添加了域名. vps也开放了7100, 7200端口，就是修改了这个。 ``` [[proxies]] name = "http_nas_101688" # name 唯一字段，不能和服务器上其他用户的服务名重复。 type = "http" # http 协议 localIP = "10.168.1.100" # 需要穿透出去的服务 IP，例如群晖的 IP。...

> I want to finetune this model on my own two datasets. One is from raw single image to 3D meshes, and the other is from text (my own feature...

> g_buffer_objaverse.py Thank you so much for your reply, I wonder to known whether is possible to generate normal map only according to the camera extrinsics and intrinsics ? For...